poll_events

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint=true, yet the description discloses non-obvious runtime behavior beyond that: events can be delivered more than once and must be deduped by eventId, and truncated=true signals skipped events due to maxAgeMs or Event Gateway retention. It also warns that the first call returns no events, only a cursor, which prevents a common misinterpretation of an empty result.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense and front-loaded: the core purpose comes first, followed by the calling protocol, then the return-value caveats, then sibling routing. Nearly every clause carries actionable information (dedupe key, poll timing, truncation cause), with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the burden of explaining the returned fields (cursor, hasMore, nextPollMs, truncated) and does so. Combined with the nested 'arguments' object being explained via list_sources inputSchema, an agent has everything needed to call and iterate correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: the omit-cursor behavior ('start from now, first call returns no events, only a cursor') and the link between maxAgeMs and the truncated flag. It does not restate maxEvents limits, but the schema already handles those.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Get events that happened since your cursor') and immediately scopes it to 'clients that can't subscribe with MCP Events (events/subscribe)', distinguishing it from the subscription mechanism. The closing sentences name both sibling alternatives (wait_for_event for blocking waits, list_events for history), so an agent can place the tool precisely among its siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit call sequence: first without a cursor to start from now, then with the returned cursor, and a concrete polling cadence ('at once when hasMore is true, otherwise after nextPollMs'). It also names when to use alternatives instead — wait_for_event to block for one event, list_events for past events — so both when-to-use and when-not-to-use are covered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.